https://github.com/kzhuravl approved this pull request.
Looks like it is reapplying 94647 (which was already reviewed) with issues
fixed. Thanks!
https://github.com/llvm/llvm-project/pull/118907
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
@@ -576,6 +576,12 @@ Generic processor code objects are versioned. See
:ref:`amdgpu-generic-processor
- ``v_dot2_f32_f16``
+ ``gfx9-4-generic`` ``amdgcn`` - ``gfx940`
https://github.com/kzhuravl commented:
Also remove EF_AMDGPU_MACH_AMDGCN_RESERVED_0X55
https://github.com/llvm/llvm-project/pull/94534
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/kzhuravl closed
https://github.com/llvm/llvm-project/pull/94483
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -121,6 +121,11 @@ enum class CudaArch {
GFX1151,
GFX1200,
GFX1201,
+ GFX9_GENERIC,
kzhuravl wrote:
Done.
https://github.com/llvm/llvm-project/pull/94483
___
cfe-commits mailing list
cfe-commits@lists.llvm.
https://github.com/kzhuravl updated
https://github.com/llvm/llvm-project/pull/94483
>From 7d64f16e9bdc6b9a195a332a49e5fb9954d5f7c1 Mon Sep 17 00:00:00 2001
From: Konstantin Zhuravlyov
Date: Wed, 5 Jun 2024 11:10:41 -0400
Subject: [PATCH 1/2] AMDGPU: Add missing gfx* generic targets handling in
https://github.com/kzhuravl created
https://github.com/llvm/llvm-project/pull/94483
None
>From 7d64f16e9bdc6b9a195a332a49e5fb9954d5f7c1 Mon Sep 17 00:00:00 2001
From: Konstantin Zhuravlyov
Date: Wed, 5 Jun 2024 11:10:41 -0400
Subject: [PATCH] AMDGPU: Add missing gfx* generic targets handling i
https://github.com/kzhuravl closed
https://github.com/llvm/llvm-project/pull/93875
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/kzhuravl updated
https://github.com/llvm/llvm-project/pull/93875
>From be005a9baf0e7f0ae7b28b96ef7e562158800af4 Mon Sep 17 00:00:00 2001
From: Konstantin Zhuravlyov
Date: Thu, 30 May 2024 16:27:42 -0400
Subject: [PATCH 1/3] AMDGPU: Add gfx12-generic target
---
clang/test/Dr
https://github.com/kzhuravl updated
https://github.com/llvm/llvm-project/pull/93875
>From be005a9baf0e7f0ae7b28b96ef7e562158800af4 Mon Sep 17 00:00:00 2001
From: Konstantin Zhuravlyov
Date: Thu, 30 May 2024 16:27:42 -0400
Subject: [PATCH 1/2] AMDGPU: Add gfx12-generic target
---
clang/test/Dr
https://github.com/kzhuravl created
https://github.com/llvm/llvm-project/pull/93875
None
>From be005a9baf0e7f0ae7b28b96ef7e562158800af4 Mon Sep 17 00:00:00 2001
From: Konstantin Zhuravlyov
Date: Thu, 30 May 2024 16:27:42 -0400
Subject: [PATCH] AMDGPU: Add gfx12-generic target
---
clang/test/
https://github.com/kzhuravl approved this pull request.
Thanks!
https://github.com/llvm/llvm-project/pull/81718
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/kzhuravl approved this pull request.
Looks good, thanks!
https://github.com/llvm/llvm-project/pull/76954
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/kzhuravl edited
https://github.com/llvm/llvm-project/pull/76955
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/kzhuravl approved this pull request.
LGTM! Thanks!
https://github.com/llvm/llvm-project/pull/76955
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -44,8 +44,15 @@ constexpr uint32_t VersionMajorV5 = 1;
/// HSA metadata minor version for code object V5.
constexpr uint32_t VersionMinorV5 = 2;
+/// HSA metadata major version for code object V6.
+constexpr uint32_t VersionMajorV6 = 1;
+/// HSA metadata minor version for c
@@ -49,6 +49,11 @@ constexpr uint32_t VersionMajorV5 = 1;
/// HSA metadata minor version for code object V5.
constexpr uint32_t VersionMinorV5 = 2;
+/// HSA metadata major version for code object V6.
+constexpr uint32_t VersionMajorV6 = 1;
+/// HSA metadata minor version for c
@@ -4135,6 +4283,33 @@ Code object V5 metadata is the same as
== == =
+.. _amdgpu-amdhsa-code-object-metadata-v6:
+
+Code Object V6 Metadata
+
+.. warning::
+ Code object
@@ -520,6 +520,106 @@ Every processor supports every OS ABI (see
:ref:`amdgpu-os`) with the following
=== === = =
=== === ==
+Generic processors also exist. They group mult
@@ -253,6 +274,12 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1151: return {11, 5, 1};
case GK_GFX1200: return {12, 0, 0};
case GK_GFX1201: return {12, 0, 1};
+
+ // Generic targets use the earliest ISA version in their group.
@@ -620,6 +620,15 @@ void ScalarBitSetTraits::bitset(IO &IO,
BCase(EF_AMDGPU_FEATURE_XNACK_V3);
BCase(EF_AMDGPU_FEATURE_SRAMECC_V3);
break;
+case ELF::ELFABIVERSION_AMDGPU_HSA_V6:
kzhuravl wrote:
I think we'd need to add a test for this?
@@ -44,8 +44,15 @@ constexpr uint32_t VersionMajorV5 = 1;
/// HSA metadata minor version for code object V5.
constexpr uint32_t VersionMinorV5 = 2;
+/// HSA metadata major version for code object V6.
+constexpr uint32_t VersionMajorV6 = 1;
+/// HSA metadata minor version for c
@@ -2585,7 +2585,7 @@ getAMDGPUCodeObjectArgument(const Driver &D, const
llvm::opt::ArgList &Args) {
void tools::checkAMDGPUCodeObjectVersion(const Driver &D,
const llvm::opt::ArgList &Args) {
const unsigned MinCodeObjVer = 4;
- cons
@@ -253,6 +274,12 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1151: return {11, 5, 1};
case GK_GFX1200: return {12, 0, 0};
case GK_GFX1201: return {12, 0, 1};
+
+ // Generic targets use the earliest ISA version in their group.
kzhuravl wrote:
@t-tye, can you please help reviewing the documentation?
https://github.com/llvm/llvm-project/pull/76955
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
kzhuravl wrote:
@AlexVlx, can you please go over versioning?
https://github.com/llvm/llvm-project/pull/76955
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
kzhuravl wrote:
> @arsenm Hi, can you take a look - especially on the testing? I don't know if
> this is tested well enough
I have not looked at the tests thoroughly. Would adding tests that make sure
trimmed features are not used in generics be beneficial? E.g. testing that
generic-gfx9 does
@@ -280,6 +295,11 @@ def : ProcessorModel<"gfx1151", GFX11SpeedModel,
FeatureISAVersion11_5_1.Features
>;
+// [gfx1100, gfx1101, gfx1102, gfx1103, 1150, 1151]
kzhuravl wrote:
gfx1150, gfx1151
https://github.com/llvm/llvm-project/pull/76955
@@ -787,11 +788,15 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX942= 0x04c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
EF_AMDGPU_MACH_AMDGCN_GFX1201 = 0x04e,
+ EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC = 0x04f,
kzhuravl wrote:
If you coul
@@ -253,6 +274,12 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1151: return {11, 5, 1};
case GK_GFX1200: return {12, 0, 0};
case GK_GFX1201: return {12, 0, 1};
+
+ // Generic targets use the earliest ISA version in their group.
@@ -787,11 +788,15 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX942= 0x04c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
EF_AMDGPU_MACH_AMDGCN_GFX1201 = 0x04e,
+ EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC = 0x04f,
+ EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC =
@@ -49,6 +49,11 @@ constexpr uint32_t VersionMajorV5 = 1;
/// HSA metadata minor version for code object V5.
constexpr uint32_t VersionMinorV5 = 2;
+/// HSA metadata major version for code object V5.
+constexpr uint32_t VersionMajorV6 = 1;
+/// HSA metadata minor version for c
@@ -280,6 +295,11 @@ def : ProcessorModel<"gfx1151", GFX11SpeedModel,
FeatureISAVersion11_5_1.Features
>;
+// [gfx1100, gfx1101, gfx1102, gfx1103, 1150, 1151]
+def : ProcessorModel<"gfx11-generic", GFX11SpeedModel,
+ FeatureISAVersion11_Generic.Features
+>;
+
//===---
@@ -787,11 +788,15 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX942= 0x04c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
EF_AMDGPU_MACH_AMDGCN_GFX1201 = 0x04e,
+ EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC = 0x04f,
+ EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC =
@@ -49,6 +49,11 @@ constexpr uint32_t VersionMajorV5 = 1;
/// HSA metadata minor version for code object V5.
constexpr uint32_t VersionMinorV5 = 2;
+/// HSA metadata major version for code object V5.
kzhuravl wrote:
Typo, did you mean V6?
https://github.com/
@@ -787,11 +788,15 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX942= 0x04c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
EF_AMDGPU_MACH_AMDGCN_GFX1201 = 0x04e,
+ EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC = 0x04f,
kzhuravl wrote:
0x04f is al
@@ -840,6 +845,12 @@ enum : unsigned {
EF_AMDGPU_FEATURE_SRAMECC_OFF_V4 = 0x800,
// SRAMECC is on.
EF_AMDGPU_FEATURE_SRAMECC_ON_V4 = 0xc00,
+
+ // Generic target versioning. This is contained in the list byte of EFLAGS.
kzhuravl wrote:
Should the versio
https://github.com/kzhuravl approved this pull request.
This LGTM. But wait a couple of days to see if @arsenm or @yxsamliu have any
objections?
https://github.com/llvm/llvm-project/pull/67118
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
ht
Author: Konstantin Zhuravlyov
Date: 2023-05-10T11:51:06-04:00
New Revision: 9d0572797233857397f3fdc35fffcfb490354f56
URL:
https://github.com/llvm/llvm-project/commit/9d0572797233857397f3fdc35fffcfb490354f56
DIFF:
https://github.com/llvm/llvm-project/commit/9d0572797233857397f3fdc35fffcfb490354f
Author: Konstantin Zhuravlyov
Date: 2023-05-10T11:51:06-04:00
New Revision: 1fc70210a6a585bad941f64bd3fca7909eeafdda
URL:
https://github.com/llvm/llvm-project/commit/1fc70210a6a585bad941f64bd3fca7909eeafdda
DIFF:
https://github.com/llvm/llvm-project/commit/1fc70210a6a585bad941f64bd3fca7909eeafd
Author: Konstantin Zhuravlyov
Date: 2021-06-04T13:10:00-04:00
New Revision: 4d9f8527dbfbc998baf35eec868c9dec1f8d1224
URL:
https://github.com/llvm/llvm-project/commit/4d9f8527dbfbc998baf35eec868c9dec1f8d1224
DIFF:
https://github.com/llvm/llvm-project/commit/4d9f8527dbfbc998baf35eec868c9dec1f8d12
Author: Konstantin Zhuravlyov
Date: 2020-10-15T14:03:26-04:00
New Revision: 67f189e93ce3c25db74697551a77831a72b34929
URL:
https://github.com/llvm/llvm-project/commit/67f189e93ce3c25db74697551a77831a72b34929
DIFF:
https://github.com/llvm/llvm-project/commit/67f189e93ce3c25db74697551a77831a72b349
Author: Konstantin Zhuravlyov
Date: 2020-10-13T12:20:28-04:00
New Revision: e2eaa914514c26c8e51c76148996a2e9cf74613c
URL:
https://github.com/llvm/llvm-project/commit/e2eaa914514c26c8e51c76148996a2e9cf74613c
DIFF:
https://github.com/llvm/llvm-project/commit/e2eaa914514c26c8e51c76148996a2e9cf7461
Author: Konstantin Zhuravlyov
Date: 2020-10-09T08:29:53-04:00
New Revision: b581c5a42f052d4d02f1152d0e1ff2d54668e6a0
URL:
https://github.com/llvm/llvm-project/commit/b581c5a42f052d4d02f1152d0e1ff2d54668e6a0
DIFF:
https://github.com/llvm/llvm-project/commit/b581c5a42f052d4d02f1152d0e1ff2d54668e6
Author: kzhuravl
Date: Mon Mar 25 13:54:00 2019
New Revision: 356947
URL: http://llvm.org/viewvc/llvm-project?rev=356947&view=rev
Log:
AMDGPU: Add support for cross address space synchronization scopes (clang)
Differential Revision: https://reviews.llvm.org/D59494
Modified:
cfe/trunk/lib/Cod
Author: kzhuravl
Date: Wed Mar 6 12:54:48 2019
New Revision: 355549
URL: http://llvm.org/viewvc/llvm-project?rev=355549&view=rev
Log:
AMDGPU: Fix the mapping of sub group sync scope
Map memory_scope_sub_group to "wavefront" sync scope
Differential Revision: https://reviews.llvm.org/D58847
Modi
Author: kzhuravl
Date: Mon Nov 5 14:44:59 2018
New Revision: 346178
URL: http://llvm.org/viewvc/llvm-project?rev=346178&view=rev
Log:
AMDGPU: Add sram-ecc feature options
Differential Revision: https://reviews.llvm.org/D53223
Modified:
cfe/trunk/include/clang/Driver/Options.td
cfe/trunk
Author: kzhuravl
Date: Wed Oct 24 12:07:56 2018
New Revision: 345181
URL: http://llvm.org/viewvc/llvm-project?rev=345181&view=rev
Log:
AMDGPU: Handle gfx909 in AMDGPUTargetInfo::initFeatureMap
+ add required tests
Modified:
cfe/trunk/lib/Basic/Targets/AMDGPU.cpp
cfe/trunk/test/Driver/amd
Author: kzhuravl
Date: Wed Oct 17 14:39:12 2018
New Revision: 344711
URL: http://llvm.org/viewvc/llvm-project?rev=344711&view=rev
Log:
AMDGPU: Add options to enable/disable code object v3
Differential Revision: https://reviews.llvm.org/D53386
Modified:
cfe/trunk/include/clang/Driver/Options.
Author: kzhuravl
Date: Tue Jul 31 18:32:21 2018
New Revision: 338471
URL: http://llvm.org/viewvc/llvm-project?rev=338471&view=rev
Log:
AMDGPU: Add clamp bit to dot builtins
Differential Revision: https://reviews.llvm.org/D50011
Added:
cfe/trunk/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err
Author: kzhuravl
Date: Fri Jul 20 13:46:25 2018
New Revision: 337612
URL: http://llvm.org/viewvc/llvm-project?rev=337612&view=rev
Log:
AMDGPU: Switch default dwarf version to 2
There were some problems unearthed with version 5,
which I am going to look at.
Differential Revision: https://reviews.
Author: kzhuravl
Date: Thu Jun 21 13:27:47 2018
New Revision: 335287
URL: http://llvm.org/viewvc/llvm-project?rev=335287&view=rev
Log:
AMDGPU: Remove amdgpu-debugger-reserve-regs feature
Modified:
cfe/trunk/lib/Driver/ToolChains/AMDGPU.cpp
cfe/trunk/test/Driver/amdgpu-features.c
Modifie
Author: kzhuravl
Date: Tue Feb 27 16:27:00 2018
New Revision: 326278
URL: http://llvm.org/viewvc/llvm-project?rev=326278&view=rev
Log:
AMDGPU: Move run and check lines around to match processor order in AMDGPU.h
Modified:
cfe/trunk/test/Driver/amdgpu-mcpu.cl
Modified: cfe/trunk/test/Driver/a
Author: kzhuravl
Date: Tue Feb 27 13:48:05 2018
New Revision: 326254
URL: http://llvm.org/viewvc/llvm-project?rev=326254&view=rev
Log:
AMDGPU: Define FP_FAST_FMA{F} macros for amdgcn
- Expand GK_*s (i.e. GFX6 -> GFX600, GFX601, etc.)
- This allows us to choose features correctly in some cases (
Author: kzhuravl
Date: Wed Feb 14 18:37:04 2018
New Revision: 325203
URL: http://llvm.org/viewvc/llvm-project?rev=325203&view=rev
Log:
Reapply r325193
Added:
cfe/trunk/test/Driver/amdgpu-macros.cl
- copied unchanged from r325199, cfe/trunk/test/Driver/amdgpu-macros.cl
Modified:
cfe/
I did not see this. I will reapply the patch. Sorry for the noise.
From: cfe-commits on behalf of Richard
Smith via cfe-commits
Sent: Wednesday, February 14, 2018 8:01 PM
To: cfe-commits@lists.llvm.org
Subject: r325195 - Add missing definition for class static af
Author: kzhuravl
Date: Wed Feb 14 18:27:45 2018
New Revision: 325200
URL: http://llvm.org/viewvc/llvm-project?rev=325200&view=rev
Log:
Revert r325193 as it breaks buildbots
Removed:
cfe/trunk/test/Driver/amdgpu-macros.cl
Modified:
cfe/trunk/lib/Basic/Targets/AMDGPU.cpp
cfe/trunk/lib/B
Author: kzhuravl
Date: Wed Feb 14 17:01:53 2018
New Revision: 325196
URL: http://llvm.org/viewvc/llvm-project?rev=325196&view=rev
Log:
AMDGPU: Enable PIC by default for amdgcn
Differential Revision: https://reviews.llvm.org/D43094
Added:
cfe/trunk/test/Driver/amdgcn-toolchain-pic.cl
Modified
Author: kzhuravl
Date: Wed Feb 14 16:20:26 2018
New Revision: 325193
URL: http://llvm.org/viewvc/llvm-project?rev=325193&view=rev
Log:
AMDGPU: Cleanup most of the macros
- Insert __AMD__ macro
- Insert __AMDGPU__ macro
- Insert __devicename__ macro
- Add missing tests for arch macros
Differentia
Author: kzhuravl
Date: Thu Feb 8 23:02:28 2018
New Revision: 324714
URL: http://llvm.org/viewvc/llvm-project?rev=324714&view=rev
Log:
AMDGPU/GCN: Bring processors in sync with AMDGPUUsage
- Remove gfx800
- Remove gfx804
- Remove gfx901
- Remove gfx903
Differential Revision: https://reviews.llvm
Author: kzhuravl
Date: Fri Nov 10 11:28:25 2017
New Revision: 317917
URL: http://llvm.org/viewvc/llvm-project?rev=317917&view=rev
Log:
AMDGPU: Add -mxnack/-mno-xnack options that set +/-xnack feature
Differential Revision: https://reviews.llvm.org/D39878
Modified:
cfe/trunk/include/clang/Dri
Author: kzhuravl
Date: Fri Nov 10 11:09:57 2017
New Revision: 317909
URL: http://llvm.org/viewvc/llvm-project?rev=317909&view=rev
Log:
AMDGPU/NFC: Move getAMDGPUTargetFeatures to AMDGPU toolchain
Differential Revision: https://reviews.llvm.org/D39877
Modified:
cfe/trunk/lib/Driver/ToolChains
Author: kzhuravl
Date: Sat Oct 14 15:24:31 2017
New Revision: 315831
URL: http://llvm.org/viewvc/llvm-project?rev=315831&view=rev
Log:
Revert "Mark test as unsupported until r315808 is fixed"
Test is fixed in r315830
Modified:
cfe/trunk/test/Misc/backend-resource-limit-diagnostics.cl
Modifi
Author: kzhuravl
Date: Fri Sep 8 09:17:16 2017
New Revision: 312795
URL: http://llvm.org/viewvc/llvm-project?rev=312795&view=rev
Log:
Add '\n' in ClangDataCollectorsEmitter
Differential Revision: https://reviews.llvm.org/D37599
Modified:
cfe/trunk/utils/TableGen/ClangDataCollectorsEmitter.c
Author: kzhuravl
Date: Fri Aug 18 10:29:07 2017
New Revision: 311178
URL: http://llvm.org/viewvc/llvm-project?rev=311178&view=rev
Log:
AMDGPU: Rename r600-mcpu.cl->amdgpu-mcpu.cl
Added:
cfe/trunk/test/Driver/amdgpu-mcpu.cl
Removed:
cfe/trunk/test/Driver/r600-mcpu.cl
Added: cfe/trunk/test
Author: kzhuravl
Date: Thu Aug 17 18:13:39 2017
New Revision: 311141
URL: http://llvm.org/viewvc/llvm-project?rev=311141&view=rev
Log:
AMDGPU: add missing amdgcn processors and tests
- gfx600
- gfx601
- gfx703
- gfx902
- gfx903
Differential Revision: https://reviews.llvm.org/D36771
Mo
Author: kzhuravl
Date: Wed Jul 26 14:59:45 2017
New Revision: 309193
URL: http://llvm.org/viewvc/llvm-project?rev=309193&view=rev
Log:
Convert mac file format to unix
Differential Revision: https://reviews.llvm.org/D35900
Modified:
cfe/trunk/include/clang/Lex/VariadicMacroSupport.h
Modified
Author: kzhuravl
Date: Tue Jul 11 15:23:37 2017
New Revision: 307723
URL: http://llvm.org/viewvc/llvm-project?rev=307723&view=rev
Log:
Enhance synchscope representation (clang)
Relevant changes required for r307722.
Differential Revision: https://reviews.llvm.org/D33109
Modified:
cfe/trunk
Author: kzhuravl
Date: Fri May 26 16:08:20 2017
New Revision: 304033
URL: http://llvm.org/viewvc/llvm-project?rev=304033&view=rev
Log:
Resubmit r303861.
[AMDGPU] add __builtin_amdgcn_s_getpc
Patch by Tim Corringham
Modified:
cfe/trunk/include/clang/Basic/BuiltinsAMDGPU.def
cfe/trunk/tes
Author: kzhuravl
Date: Fri Apr 14 00:33:57 2017
New Revision: 300306
URL: http://llvm.org/viewvc/llvm-project?rev=300306&view=rev
Log:
[AMDGPU][GFX9] Set +fp32-denormals for >=gfx900 unless -cl-denorms-are-zero is
set
Differential Revision: https://reviews.llvm.org/D31482
Added:
cfe/trunk/t
Author: kzhuravl
Date: Tue Mar 21 13:55:39 2017
New Revision: 298420
URL: http://llvm.org/viewvc/llvm-project?rev=298420&view=rev
Log:
Fix array sizes where address space is not yet known
For variables in generic address spaces, for example:
```
unsigned char V[6442450944];
...
```
the address
Author: kzhuravl
Date: Thu Mar 9 12:06:23 2017
New Revision: 297397
URL: http://llvm.org/viewvc/llvm-project?rev=297397&view=rev
Log:
[DebugInfo] Append extended dereferencing mechanism to variables' DIExpression
for targets that support more than one address space
Differential Revision: https:
Author: kzhuravl
Date: Wed Mar 8 18:14:57 2017
New Revision: 297329
URL: http://llvm.org/viewvc/llvm-project?rev=297329&view=rev
Log:
Driver/ToolChains: Remove extra semicolons. NFC
Modified:
cfe/trunk/lib/Driver/ToolChains/Haiku.cpp
cfe/trunk/lib/Driver/ToolChains/TCE.cpp
cfe/trunk/
Author: kzhuravl
Date: Wed Mar 8 17:56:48 2017
New Revision: 297321
URL: http://llvm.org/viewvc/llvm-project?rev=297321&view=rev
Log:
[DebugInfo] Add address space when creating DIDerivedTypes
Differential Revision: https://reviews.llvm.org/D29671
Added:
cfe/trunk/test/CodeGenOpenCL/amdgpu-
Author: kzhuravl
Date: Wed Mar 8 16:36:04 2017
New Revision: 297312
URL: http://llvm.org/viewvc/llvm-project?rev=297312&view=rev
Log:
Driver/ToolChains: Mips -> MipsLinux
- Mips is architecture, not a toolchain
- Might help eliminate the confusion in the future by not having header files
wit
Author: kzhuravl
Date: Fri Jan 6 10:14:41 2017
New Revision: 291243
URL: http://llvm.org/viewvc/llvm-project?rev=291243&view=rev
Log:
[OpenCL] Re-enable supported core extensions based on opencl version when
disabling all extensions using pragma
Differential Revision: https://reviews.llvm.org/D
This revision was automatically updated to reflect the committed changes.
Closed by commit rL287390: [AMDGPU] Change frexp.exp builtin to return i16 for
f16 input (authored by kzhuravl).
Changed prior to commit:
https://reviews.llvm.org/D26863?vs=78546&id=78586#toc
Repository:
rL LLVM
https
Author: kzhuravl
Date: Fri Nov 18 16:31:51 2016
New Revision: 287390
URL: http://llvm.org/viewvc/llvm-project?rev=287390&view=rev
Log:
[AMDGPU] Change frexp.exp builtin to return i16 for f16 input
Differential Revision: https://reviews.llvm.org/D26863
Modified:
cfe/trunk/include/clang/Basic/
kzhuravl created this revision.
kzhuravl added reviewers: tstellarAMD, arsenm.
kzhuravl added subscribers: b-sumner, cfe-commits.
Herald added subscribers: tony-tye, yaxunl, nhaehnle, wdng.
https://reviews.llvm.org/D26863
Files:
include/clang/Basic/BuiltinsAMDGPU.def
lib/CodeGen/CGBuiltin.cpp
This revision was automatically updated to reflect the committed changes.
Closed by commit rL286741: [AMDGPU] Add f16 builtin functions (VI+) (authored
by kzhuravl).
Changed prior to commit:
https://reviews.llvm.org/D26476?vs=77654&id=77732#toc
Repository:
rL LLVM
https://reviews.llvm.org/D
Author: kzhuravl
Date: Sat Nov 12 20:37:05 2016
New Revision: 286741
URL: http://llvm.org/viewvc/llvm-project?rev=286741&view=rev
Log:
[AMDGPU] Add f16 builtin functions (VI+)
Differential Revision: https://reviews.llvm.org/D26476
Added:
cfe/trunk/test/SemaOpenCL/builtins-amdgcn-error-f16.cl
kzhuravl updated this revision to Diff 77654.
kzhuravl added a comment.
Leave the return type of `frexp_exph` unchanged
https://reviews.llvm.org/D26476
Files:
include/clang/Basic/BuiltinsAMDGPU.def
lib/CodeGen/CGBuiltin.cpp
test/CodeGenOpenCL/builtins-amdgcn-error.cl
test/CodeGenOpenCL/
kzhuravl updated this revision to Diff 77634.
kzhuravl added a comment.
Also update run line to exclude `amdhsa` from another error file.
https://reviews.llvm.org/D26476
Files:
include/clang/Basic/BuiltinsAMDGPU.def
lib/CodeGen/CGBuiltin.cpp
test/CodeGenOpenCL/builtins-amdgcn-error.cl
t
kzhuravl updated this revision to Diff 77633.
kzhuravl marked 4 inline comments as done.
kzhuravl added a comment.
Address review feedback: put tests in the same file, update run line, move
error tests to SemaOpenCL directory
https://reviews.llvm.org/D26476
Files:
include/clang/Basic/Builtin
kzhuravl added inline comments.
Comment at: test/CodeGenOpenCL/builtins-amdgcn-error-f16-class.cl:1-9
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-amdhsa -target-cpu tahiti -verify -S
-o - %s
+
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+
kzhuravl created this revision.
kzhuravl added reviewers: tstellarAMD, arsenm.
kzhuravl added a subscriber: cfe-commits.
Herald added subscribers: tony-tye, yaxunl, nhaehnle, wdng.
https://reviews.llvm.org/D26476
Files:
include/clang/Basic/BuiltinsAMDGPU.def
lib/CodeGen/CGBuiltin.cpp
test/C
Author: kzhuravl
Date: Sun Sep 25 20:02:57 2016
New Revision: 282371
URL: http://llvm.org/viewvc/llvm-project?rev=282371&view=rev
Log:
[AMDGPU] Expose flat work group size, register and wave control attributes
__attribute__((amdgpu_flat_work_group_size(, ))) - request minimum
and maximum flat wo
This revision was automatically updated to reflect the committed changes.
Closed by commit rL282371: [AMDGPU] Expose flat work group size, register and
wave control attributes (authored by kzhuravl).
Changed prior to commit:
https://reviews.llvm.org/D24513?vs=71970&id=72436#toc
Repository:
r
kzhuravl added a comment.
Thanks for the review Aaron!
Tom, would you be able to do a final glance over?
https://reviews.llvm.org/D24513
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-comm
kzhuravl added inline comments.
Comment at: lib/Sema/SemaDeclAttr.cpp:4967
@@ +4966,3 @@
+
+ D->addAttr(::new (S.Context)
+ AMDGPUFlatWorkGroupSizeAttr(Attr.getLoc(), S.Context, Min, Max,
aaron.ballman wrote:
> Is it okay to supply `0, 0` as the min,
kzhuravl updated this revision to Diff 71970.
kzhuravl added a comment.
Herald added a subscriber: kzhuravl.
Mention `0, 0` case in the docs.
https://reviews.llvm.org/D24513
Files:
include/clang/Basic/Attr.td
include/clang/Basic/AttrDocs.td
include/clang/Basic/DiagnosticSemaKinds.td
lib
kzhuravl added inline comments.
Comment at: include/clang/Basic/Attr.td:1067
@@ +1066,3 @@
+ let Spellings = [GNU<"amdgpu_waves_per_eu">];
+ let Args = [UnsignedArgument<"Min">, VariadicUnsignedArgument<"Max">];
+ let Documentation = [AMDGPUWavesPerEUDocs];
aar
kzhuravl updated this revision to Diff 71449.
kzhuravl marked 15 inline comments as done.
kzhuravl added a comment.
Address review feedback
https://reviews.llvm.org/D24513
Files:
include/clang/Basic/Attr.td
include/clang/Basic/AttrDocs.td
include/clang/Basic/DiagnosticSemaKinds.td
lib/C
kzhuravl updated this revision to Diff 71382.
kzhuravl added a comment.
Fix minor typos
https://reviews.llvm.org/D24513
Files:
include/clang/Basic/Attr.td
include/clang/Basic/AttrDocs.td
include/clang/Basic/DiagnosticSemaKinds.td
lib/CodeGen/TargetInfo.cpp
lib/Sema/SemaDeclAttr.cpp
kzhuravl updated the summary for this revision.
kzhuravl updated this revision to Diff 71311.
kzhuravl added a comment.
Update docs in AttrDocs.td
https://reviews.llvm.org/D24513
Files:
include/clang/Basic/Attr.td
include/clang/Basic/AttrDocs.td
include/clang/Basic/DiagnosticSemaKinds.td
kzhuravl created this revision.
kzhuravl added reviewers: arsenm, aaron.ballman.
kzhuravl added subscribers: yaxunl, kanarayan, cfe-commits.
Herald added a reviewer: tstellarAMD.
Herald added subscribers: nhaehnle, wdng.
__attribute__((amdgpu_flat_work_group_size(, ))) - request minimum
and maxim
kzhuravl abandoned this revision.
kzhuravl added a comment.
This patch is not required at this point since we left SynchronizationScope
enum intact and did not rename existing members
https://reviews.llvm.org/D21724
___
cfe-commits mailing list
cfe
kzhuravl updated this revision to Diff 65343.
kzhuravl added a comment.
Remove metadata generation
https://reviews.llvm.org/D21724
Files:
lib/CodeGen/CGBuiltin.cpp
Index: lib/CodeGen/CGBuiltin.cpp
===
--- lib/CodeGen/CGBuiltin.c
kzhuravl updated this revision to Diff 62971.
kzhuravl added a comment.
Rebase
http://reviews.llvm.org/D21724
Files:
lib/CodeGen/CGBuiltin.cpp
lib/CodeGen/CodeGenModule.cpp
lib/CodeGen/CodeGenModule.h
test/CodeGen/synchscopes.cpp
Index: test/CodeGen/synchscopes.cpp
kzhuravl created this revision.
kzhuravl added reviewers: tstellarAMD, arsenm, rampitec.
kzhuravl added subscribers: cfe-commits, llvm-commits, resistor.
As described in this proposal:
https://groups.google.com/forum/#!topic/llvm-dev/GtWfCc5j-4U
http://reviews.llvm.org/D21724
Files:
lib/CodeG
1 - 100 of 127 matches
Mail list logo
